For product managers

Refine and triage GitHub backlog by finding open issues that are stale, obsolete, or resolved by another path.

axelixlabs/axelix

A skill your agent uses when the user asks "show me X", "demo X", "walk me through X", "how X works" or requests a live feature demonstration from a spec, feature or ticket.

LIDR-academy/AI4Devs-LTI-extended

Session retrospective for improving marimo-pair and marimo.codemode.

PhySpace/SimpleCADAPI

Competitive gap analysis for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-002).

acogood/diffmode_free

从 task-plan 任务产物（prd.md、feature.md、research/.md、progress.csv）中提炼可复用工程经验，写入 docs/KB/ 知识库。

VkRainB/ccMesh

Score a codebase, file, or merge request against the FIASSE v1.0.4 SSEM model — 0-10 per attribute, equal-weighted pillars, evidence-backed strengths and weaknesses, prioritized recommendations…

OWASP/secure-agent-playbook

Turn a process description into an operational quality-control checklist — binary pass/fail checks, acceptance criteria, critical-vs-routine tiers, and failure modes with catch-points.

sgharlow/claude-code-recipes

Plan customer discovery, turn interview snapshots into synthesis and evidence-based opportunities, build or update an Opportunity Solution Tree, map jobs and segments, and design RAT tests for the…

andreaskelm/pm-brain

Learn from public breach disclosures — extract the audit question each one implies and check your own stack.

briiirussell/cybersecurity-skills

Creates a clear problem framing document with user impact, business context, and success criteria.

product-on-purpose/pm-skills

Diagnose project complexity from a rough project description using the DelftX TOE framework and detail/dynamic complexity model.

maiobarbero/my-ai-workflow

A skill your agent uses when the user wants to turn an application, product, startup idea, SaaS, mobile app, web app, API, AI product, or internal tool into a production-ready Markdown specification…

instructa/agent-skills

Implement all items for a specific version in the pgtrickle roadmap.

trickle-labs/pg-trickle

同步历史 PRD/需求文档。先修正旧知识文件格式，再从 PRD 中提取业务概念，对照当前代码确认实际实现，合并更新 .repomind/concepts/ 的业务卡片与元数据；必要时再交给 repomind-summary 补充模块侧知识。

HobbyBear/tinydocker

Looks up kanban boards and task status through two bash-invoked tools instead of guessing, listing boards first and then filtering tasks by status, board or assistant.

YaoApp/yao

チーム全体で統一された開発プロセスとコーディング規約を確立するための包括的なガイドとテンプレート。開発ガイドライン作成時、コード実装時に使用する。

GenerativeAgents/claude-code-book-chapter8

Deliver Invokta milestones and work items with TDD, adherence to versioned contracts and architecture, complete validation, and one cohesive commit per work item.

vinilana/invokta

Analyzes uploaded cohort data to compute retention curves and feature adoption trends, builds heatmaps and charts, and suggests qualitative follow-up research.

phuryn/pm-skills

质检 Agent：检查 vibe-coding-kit 其他 Skill 的产出物是否符合治理规范. An agent skill from Junliu1066/vibe-coding-kit.

Junliu1066/vibe-coding-kit

基于Sorftime MCP的选品分析，发现高潜力市场机会、多维度属性标注与交叉分析、验证竞争格局、测算投入产出、输出Go/No-Go决策与选品报告。

zach22-1999/amazon-skills

This SKILL provides detailed instructions on how to use the planning plugin tools.

IgorWarzocha/opencode-planning-toolkit

Detect users who newly crossed a rating threshold (2000/2400/2800/3200) in a given AtCoder contest, validate whether they are listed on the site's blog pages, and report candidates for addition.

KATO-Hiro/AtCoderClans

Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback.

spec-kitty/spec-kitty

Maps the full competitive landscape — direct, indirect, substitute, and emerging competitors — with positioning gap analysis, review mining, and marketinsights-calibrated saturation scoring.

MaxKmet/idea-validation-agents

Orchestration spine and "what do I do next?" router for the BMAD Planning & Orchestrator plugin.

aj-geddes/claude-code-bmad-skills

Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint.

facebookresearch/autoform-bot

Analyze a user interview from Granola, pasted text, or a file into an evidence-backed briefing, journey insights, product findings, patterns, and actions.

egregore-labs/egregore

Review software designs and implementations for user experience, simplicity, and maintainability; apply fixes when requested.

golbin/agent-skills

Perform multi-touch attribution analysis using Markov chains, Shapley values, and custom attribution models.

liangdabiao/claude-data-analysis-ultra-main

Plan-based verification - freeze acceptance criteria before building, then verify after with an independent fresh-context agent (the builder must not verify their own work).

AnastasiyaW/codex-claude-code-config

Bring the base that every dispatched unit is cut from up to date before the first dot-agent-deck dispatch of a batch in this repo, and check the base dispatch reports afterwards.

vfarcic/dot-agent-deck

Produce a verified spec — problem, desired outcome, and acceptance criteria — before building.

getsentry/sentry-react-native

Orchestrate agile development workflows for Gitea repositories using the tea CLI.

jwynia/agent-skills

Frameworks for user interviews, question design, and qualitative research.

slgoodrich/agents

Plan the MVP build from a PRD and an MVP concept, as a full development plan or an ultra-lean build spec, with the AI Product Development Toolkit's planning prompts.

TechNomadCode/AI-Product-Development-Toolkit

Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries.

PostHog/posthog

Write a PRODUCT.md spec for a significant Hubble user-facing feature, focused only on user experience and observable behavior.

bholmesdev/hubble.md

A skill your agent uses when work starts before a complete PRD exists, including 产品前置, 产品调研, 用户调研, 竞品分析, PRD, 原型, 想法建单, 老板需求, 需求来源, 产品父单, 角色拆单, 设计子单, 前端子单, 后端子单, 页面原型 Spec, BKUI 原型, HTML 原型, 原型评审…

TencentBlueKing/bk-bcs

Sovereign-stack PRE-RELEASE protocol. An agent skill from paiml/aprender.

paiml/aprender

Forces a KEEP, CUT, or DEFER decision on every feature when scope is too large, no MVP consensus exists, or time is running out.

MAGA2010/hackathon-run

Helps an Amplitude user design a custom agent by proposing use cases that fit their role and data, shaping a spec, and returning a Global Agent link that builds it.

amplitude/builder-skills

Synthesize a PRD (Product Requirements Document) for a big new feature.

evanklem/evanflow

Walks a product manager through a customer journey map one question at a time, from persona and scenario to pain points and opportunities.

deanpeters/Product-Manager-Skills

Computational pathology toolkit for analyzing whole-slide images (WSI) and multiparametric imaging data.

davila7/claude-code-templates

Read and edit a Headway kanban board from the command line via the headway CLI (crates/headwaycli).

damus-io/notedeck

Configure, build and test PortPS5 with the pinned MinGW-w64 GCC 15.2 toolchain and ctest.

yuriolive/PortPS5

Plan work and generate ralph task files for autonomous execution.

opentabs-dev/opentabs

Compares options with pros and cons, weighted scoring, pre-mortems, opportunity costs and ICE prioritization, labeling assumptions instead of inventing numbers.

iflytek/skillhub